mergekit-community/mergekit-task_arithmetic-qjeuqjw

Full fine-tune vs BeaverLegacy/Smegmma-9B-v1. Fine-tune: 100% of the weights changed, across 42 of 42 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 105/169, MLP 126/126, Attention 168/168

2 derivatives checked

• mradermacher/mergekit-task_arithmetic-qjeuqjw-i1-GGUF: Quantization
• mradermacher/mergekit-task_arithmetic-qjeuqjw-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse